Interpreting Unfairness in Graph Neural Networks via Training Node Attribution.
Yushun DongSong WangJing MaNinghao LiuJundong LiPublished in: CoRR (2022)
Keyphrases
- neural network
- graph structure
- directed graph
- training process
- training algorithm
- feedforward neural networks
- feed forward neural networks
- multi layer perceptron
- graph representation
- random walk
- undirected graph
- back propagation
- pattern recognition
- backpropagation algorithm
- nodes of a graph
- finding the shortest path
- weighted graph
- graph model
- fuzzy logic
- edge weights
- supervised learning
- artificial neural networks
- path length
- spanning tree
- neural network training
- error back propagation
- neural nets
- genetic algorithm
- root node
- training set
- neural network structure
- overlapping communities
- activation function
- tree structure
- graph matching
- graph theory
- training samples
- radial basis function network
- training phase
- training examples
- hidden layer
- neural network model
- betweenness centrality
- multi layer